Strictly Breadth-First AMR Parsing

TL;DR

This paper introduces a new AMR parsing architecture that guarantees strict adherence to the breadth-first order during parsing, leading to improved performance on standard datasets.

Contribution

The paper proposes a novel architecture that ensures strictly breadth-first AMR parsing, addressing limitations of previous models that only encouraged but did not guarantee this order.

Findings

Achieves better performance on AMR 1.0 and 2.0 datasets.

Guarantees strict breadth-first order in parsing process.

Improves upon previous models by incorporating a focused parent vertex.

Abstract

AMR parsing is the task that maps a sentence to an AMR semantic graph automatically. We focus on the breadth-first strategy of this task, which was proposed recently and achieved better performance than other strategies. However, current models under this strategy only \emph{encourage} the model to produce the AMR graph in breadth-first order, but \emph{cannot guarantee} this. To solve this problem, we propose a new architecture that \emph{guarantees} that the parsing will strictly follow the breadth-first order. In each parsing step, we introduce a \textbf{focused parent} vertex and use this vertex to guide the generation. With the help of this new architecture and some other improvements in the sentence and graph encoder, our model obtains better performance on both the AMR 1.0 and 2.0 dataset.